Information processing device and information processing method

Abstract

The present invention provides an information processing device and an information processing method that can estimate the location of the manufacturing plant of a component manufactured by a supplier. [Solution] An information processing device comprising: a transaction relationship score calculation unit 202 that calculates an inter-industry transaction relationship score representing the relationship between transaction relationships between multiple industries; a parts supplier industry estimation unit 204 that estimates the industry of a supplier factory candidate based on parts identification information for the supplier factory candidate; an industry similarity calculation unit 205 that calculates an inter-industry transaction relationship score between the industry of the supplier factory candidate and the industry of the supplier factory candidate estimated by the parts supplier industry estimation unit; and a parts manufacturing plant estimation unit 206 that selects a supplier factory candidate based on the inter-industry transaction relationship score calculated by the industry similarity calculation unit and estimates the location of the selected supplier candidate as the location of the parts manufacturing plant that the supplier produces.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus and an information processing method. In particular, the present invention relates to an information processing apparatus and the like for estimating the location of a manufacturing plant of parts manufactured by a supplier.

Background Art

[0002] In order to grasp the supply chain, a supplier list may be created as a list of suppliers that manufacture and supply parts and the like. The current supplier list describes, as supplier information, for example, supplier name, headquarters, part name / type number, but the location of the supplier's manufacturing plant is often unknown.

[0003] Patent Document 1 discloses a recommendation apparatus that recommends companies that are potential business partners. In this apparatus, an open data collection unit collects, as open data, company information that is publicly available or sold regarding potential business partner companies and registers it in a corporate master. A business rule conversion unit collects the compliance policy, ESG policy, sales and purchase policies, policies, regulations, etc. of the transaction entity company, formulates each collected information, and registers it in a business rule master. An event evaluation unit refers to the business rule master based on past transaction performance information and external evaluation data collected by the event information collection unit, and registers the evaluation results for each evaluation axis for the business partner company in an evaluation master. When there is a recommendation request regarding a business partner company, a corporate recommendation unit refers to the corporate master, evaluation master, and business rule master and presents companies that can be recommended as business partners.

[0004] Patent Document 2 discloses a disaster and crisis management system comprising a server capable of communicating with a company's user terminal and a risk information extraction unit that detects and extracts risk information indicating risk content, including disasters and accidents, from information sources including social networking services (SNS). The server acquires risk information from the risk information extraction unit, and uses that risk information, along with a stored supplier company information database and a supplier product information database, to identify suppliers affected by the risk information. The server then generates an alert notification containing the content of the risk information, the company information of the identified supplier, the supply chain information to which the identified supplier belongs, and the product information of the identified supplier, and sends the alert notification to the user terminal. [Prior art documents] [Patent Documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2023-147907 [Patent Document 2] Japanese Patent Publication No. 2023-159850 [Overview of the Initiative] [Problems that the invention aims to solve]

[0006] For example, to assess risks to a supply chain, it is necessary to know the location of the manufacturing plants for the parts produced by suppliers. Traditionally, this had to be done by manually gathering information, which required an enormous amount of effort. The present invention aims to provide an information processing device and an information processing method that can estimate the location of a manufacturing plant for parts produced by a supplier. [Means for solving the problem]

[0007] To solve the above problems, the present invention provides an information processing device comprising: a transaction relationship score calculation unit that calculates an inter-industry transaction relationship score representing the relationship between transaction relationships between multiple industries; a parts supplier industry estimation unit that estimates the industry of a supplier's factory candidate based on parts identification information for the supplier's factory candidate; an industry similarity calculation unit that calculates an inter-industry transaction relationship score between the industry of the supplier's factory candidate and the industry of the supplier's factory candidate estimated by the parts supplier industry estimation unit; and a parts manufacturing plant estimation unit that selects a supplier's factory candidate based on the inter-industry transaction relationship score calculated by the industry similarity calculation unit and estimates the location of the selected supplier candidate as the location of the manufacturing plant for the parts manufactured by the supplier. In this case, the present invention provides an information processing device that can estimate the location of the manufacturing plant for the parts manufactured by the supplier.

[0008] Here, for example, the transaction relationship score calculation unit narrows down the supplier factory candidates based on the inter-industry transaction relationship score between the industry of the user's company and the industry of the supplier factory candidates, and then subjects the narrowed-down supplier factory candidates to processing by the parts supplier industry estimation unit. In this case, the supplier factory candidates can be narrowed down by focusing on the similarities in the industries of companies that have transaction relationships in the supply chain. Furthermore, the system includes an industry estimation unit that estimates the industry of potential supplier factories. In this case, industries can be compared using the same evaluation criteria. Furthermore, for example, the parts supplier industry estimation unit either directly estimates the industry of a potential supplier's factory from at least one of the parts name and part number, or estimates it through mapping to data in a different system. In this case, estimation can be performed by combining multiple data based on the parts name / part number. Furthermore, the system includes, for example, a parts / model number estimation unit that acquires parts information. If parts information is available, the parts supplier industry estimation unit directly estimates the industry of a potential supplier factory from at least one of the parts name and model number. If parts information cannot be acquired, it estimates the industry through mapping to data in a different system. In this case, even if the industry of a potential supplier factory cannot be directly estimated based on the parts name / model number, it can be estimated by other methods. Furthermore, data from different systems may include import / export statistical commodity codes. In this case, it becomes easier to estimate the industry of potential supplier factories. Furthermore, the system includes a corporate information search unit that searches for potential supplier factories based on a supplier list, which is a list of information about suppliers of products manufactured by the company to which the user belongs. In this case, potential supplier factories can be obtained using the supplier list. Furthermore, for example, the corporate information retrieval unit searches for potential supplier factories by using the company names of suppliers included in the supplier list as keywords. In this case, it becomes easier to obtain potential supplier factories through the search. Furthermore, for example, if a supplier included in the supplier list has not obtained official certification, the Corporate Information Retrieval Department will search for potential supplier factories. If the supplier has obtained official certification, it will estimate the industry of the supplier's factory based on the manufactured items registered in the official certification. In this case, if the supplier has obtained official certification, the industry of the supplier's factory can be estimated based on this. Even if the supplier has not obtained official certification, the Corporate Information Retrieval Department can estimate the industry of the supplier's factory by searching for potential supplier factories. For example, the parts manufacturing plant estimation unit selects the supplier's factory candidate with the highest inter-industry transaction relationship score, and estimates the location of the selected supplier's factory candidate as the location of the parts manufacturing plant that the supplier produces. In this case, the user can be presented with the location that is most likely to be the supplier's factory candidate. Furthermore, for example, the parts manufacturing plant estimation unit also selects additional supplier plant candidates that exceed a predetermined threshold. In this case, even if the estimation result is incorrect, the user can select a corrected candidate. Furthermore, for example, the transaction relationship score calculation unit calculates the inter-industry transaction relationship score based on the transaction amount between industries. In this case, a more appropriate value can be obtained as the inter-industry transaction relationship score.

[0009] Furthermore, the present invention is an information processing method in which a processor executes a program stored in memory to calculate an inter-industry relationship score representing the relationship between business relationships between multiple industries, estimates the industry of a candidate supplier's factory from the parts, calculates an inter-industry relationship score between the estimated industry of the candidate supplier's factory and the candidate supplier's factory, selects a candidate supplier's factory based on the calculated inter-industry relationship score, and estimates the location of the selected candidate supplier as the location of the factory where the supplier manufactures the parts. In this case, the present invention provides an information processing method that can estimate the location of the factory where the supplier manufactures the parts. [Effects of the Invention]

[0010] According to the present invention, it is possible to provide an information processing device and an information processing method that can estimate the location of a manufacturing plant for parts produced by a supplier. [Brief explanation of the drawing]

[0011] [Figure 1] This is a block diagram showing the overall configuration of the risk visualization system according to this embodiment. [Figure 2] This is a diagram illustrating an example of a supplier list data table that is received as input from procurement personnel. [Figure 3] This is a table diagram showing an example of search results generated by the Corporate Information Retrieval Department, using the supplier's company name as a keyword. [Figure 4] This is a table diagram of a data table that manages information about the company to which a procurement officer belongs. [Figure 5] It is a chart showing an example of a data table of transaction relationships between industries. [Figure 6] It is a chart showing an example of a data table of inter-industry transaction relationship scores. [Figure 7] It is a diagram showing the processing flow of a component manufacturing factory location estimation device in a risk visualization system. [Figure 8] It is a diagram showing a flowchart of a process for narrowing down candidate factories of a supplier. [Figure 9] It is a diagram showing the output result of a transaction relationship score calculation unit. [Figure 10] It is a diagram showing an overview of the processing flow of a component supplier industry estimation unit. [Figure 11] (It is a diagram showing the details of the processing flow of a component supplier industry estimation unit. [Figure 12] (a) It is a diagram showing a data table showing the estimation result when directly estimating the industry by part name / type number. [Figure 13] (b) It is a diagram showing a data table showing the estimation result when estimating the industry in two steps through mapping from part name / type number to data of a different system. [Figure 14] (c) It is a diagram showing a data table showing the estimation result when estimating the industry in three steps through mapping from part name / type number to data of two different systems. [Figure 15] It is a diagram showing a data table when inter-industry transaction relationship scores are assigned to the search results in FIG. 3. [Figure 16] It is a diagram showing the processing flow of a component manufacturing factory estimation unit. [Figure 17] It is a diagram showing a data table when the location of the manufacturing factory of the component estimated in S707 in FIG. 7 is reflected in the supplier list.

Embodiments for Carrying Out the Invention

[0012] The present invention will be described below with reference to the drawings. However, the present invention is not to be construed as being limited to the embodiments described below. It will be readily apparent to those skilled in the art that the specific configuration can be modified without departing from the spirit or purpose of the present invention. In the configuration of the invention described below, the same reference numerals are used in common across different drawings for parts that are the same or have similar functions, and redundant explanations may be omitted. When there are multiple elements with the same or similar function, they may be described using the same symbol but with different subscripts. However, if there is no need to distinguish between multiple elements, the subscript may be omitted in the description. In this specification, notations such as "Part 1," "Part 2," and "Part 3" are used to identify components and do not necessarily limit their number, order, or content. Furthermore, the numbers used to identify components are used on a context-by-context basis, and a number used in one context does not necessarily indicate the same component in another context. Moreover, this does not prevent a component identified by one number from also performing the function of a component identified by another number. The positions, sizes, shapes, and ranges of each component shown in drawings, etc., may not represent their actual positions, sizes, shapes, and ranges in order to facilitate understanding of the invention. Therefore, the present invention is not necessarily limited to the positions, sizes, shapes, and ranges disclosed in drawings, etc.

[0013] <Overview of Risk Visualization System 1> Figure 1 is a block diagram showing the overall configuration of the risk visualization system 1 according to this embodiment. Figure 1 is a system configuration diagram showing the application of the present invention to a risk visualization system 1 that visualizes and displays risk information affecting suppliers. The risk visualization system 1 connects to the corporate information database 300, open data 350, and user terminals 370 via the network 400.

[0014] The corporate information database 300 stores information about companies, including their suppliers. Open Data 350 is public and private data held by the national government, local governments, and businesses, and is data that anyone can easily access through Network 400. User terminal 370 is the user's terminal device. The user is, for example, a procurement officer who is a user of the risk visualization system 1. The procurement officer manages the supply chain with the aim of ensuring stability and reducing losses throughout the supply chain. The procurement officer may be a member of management or the finance department, or a member of a separate company (for example, a consulting firm or an affiliated company).

[0015] Network 400 is a communication means used for information communication between the risk visualization system 1, the corporate information database 300, the open data 350, and the user terminal 370, and is, for example, the internet, a LAN (Local Area Network), or a WAN (Wide Area Network). The communication lines used for information communication may be wired or wireless, or a combination of wired and wireless may be used. Furthermore, the risk visualization system 1, the corporate information database 300, the open data 350, and the user terminal 370 may be connected via multiple networks and communication lines using relay devices such as gateway devices and routers.

[0016] The risk visualization system 1 takes the form of connecting a parts manufacturing plant location estimation device 500 to the existing system 501. The existing system 501 is a device for estimating risks to the supply chain. The existing system 501 includes a DB (Database) server 502 that manages supply chain data and evaluates risks to the supply chain, and an application server 503 that visualizes these risks.

[0017] The DB server 502 comprises a supplier information acquisition unit 100, a risk information acquisition unit 101, a risk estimation unit 102, a corporate / risk information (data lake) 301, a corporate / risk information (data lake) 302, and a data management unit 110.

[0018] The supplier information acquisition unit 100 collects information about suppliers from the corporate information database 300 and open data 350 via the network 400. The risk information acquisition unit 101 collects risk information, which is data relating to risks that affect the supply chain. Risk information includes, for example, data relating to conflicts, and data relating to the production of minerals, oil, and natural gas. Other data relating to risks include, for example, trade statistics, news disseminated by news media, and weather data. The risk estimation unit 102 estimates the risks to the supply chain and outputs the estimation results. For example, the risk estimation unit 102 calculates a risk level, which is a numerical representation of the degree of risk for each type of risk.

[0019] The Corporate / Risk Information (Data Lake) 301 stores supplier information collected by the Supplier Information Acquisition Unit 100 as a supplier list. More details about the supplier list will be provided later. The Corporate / Risk Information (Data Lake) 301 also stores risk information collected by the Risk Information Acquisition Unit 101. Corporate / risk information (data lake) 302 acquires data from corporate / risk information (data lake) 301 and stores data with estimated results of the manufacturing plants of parts produced by suppliers. The data management unit 110 manages various types of data handled by the existing system 501.

[0020] The application server 503 includes a risk visualization screen rendering unit 111. The risk visualization screen rendering unit 111 uses an application to visualize the risk estimation results obtained by the risk estimation unit 102 and creates an image to provide to the user.

[0021] The parts manufacturing plant location estimation device 500 is an example of an information processing device that estimates the location of the manufacturing plant for parts produced by a supplier. The parts manufacturing plant location estimation device 500 acquires data from the company / risk information (data lake) 301 and stores the data with the estimated location of the parts manufacturing plant attached in the company / risk information (data lake) 302.

[0022] The parts manufacturing plant location estimation device 500 comprises a company information retrieval unit 200, an industry estimation unit 201, a transaction relationship score calculation unit 202, a parts / model number estimation unit 203, a parts supplier industry estimation unit 204, an industry similarity calculation unit 205, a parts manufacturing plant estimation unit 206, and an inter-industry similarity unit 303. As will be described in more detail later, these generally have the functions outlined below.

[0023] The Corporate Information Search Unit 200 searches for potential supplier factories based on the supplier list. In this process, the Corporate Information Search Unit 200 searches for potential supplier factories by using the company names of suppliers included in the supplier list as keywords. The industry estimation unit 201 estimates the industry of potential supplier factories.

[0024] The Transaction Relationship Score Calculation Unit 202 calculates an inter-industry transaction relationship score that represents the relationship between transaction relationships between multiple industries. The Transaction Relationship Score Calculation Unit 202 calculates the inter-industry transaction relationship score based on the transaction amount between industries. This allows for obtaining a more appropriate value as the inter-industry transaction relationship score. Furthermore, the Transaction Relationship Score Calculation Unit 202 narrows down the supplier factory candidates based on the inter-industry transaction relationship score between the industry of the user's company and the industry of the supplier factory candidates, and subjects the narrowed-down supplier factory candidates to processing by the parts supplier industry estimation unit 204. This makes it possible to narrow down the supplier factory candidates by focusing on the similarities in the industries of companies that have transaction relationships in the supply chain.

[0025] The part / model number estimation unit 203 acquires part information. The part / model number estimation unit 203 acquires part information from at least one of the part name and model number of the part listed in the supplier list. Part information includes, for example, material, price, and delivery date. The parts supplier industry estimation unit 204 estimates the industry of a candidate supplier factory based on the parts identification information. The parts identification information is not particularly limited as long as it is information that can identify the part, but in this embodiment, at least one of the part name and part number listed in the supplier list is used.

[0026] The industry similarity calculation unit 205 calculates an inter-industry transaction relationship score between the industry of the supplier's factory candidate and the industry of the supplier's factory candidate estimated by the parts supplier industry estimation unit 204. The parts manufacturing plant estimation unit 206 selects candidate supplier factories based on the inter-industry transaction relationship score calculated by the industry similarity calculation unit 205, and estimates the location of the selected supplier candidate as the location of the parts manufacturing plant that the supplier produces. The inter-industry similarity score 303 stores the inter-industry transaction relationship scores calculated by the transaction relationship score calculation unit 202 and the inter-industry similarity calculation unit 205.

[0027] The parts manufacturing plant location estimation device 500, the DB server 502, and the application server 503 are computer devices, for example, server computers. However, they are not limited to these, and may also be PCs (Personal Computers), mobile computers, smartphones, tablets, etc. They may also be cloud servers that operate on the cloud.

[0028] The parts manufacturing plant location estimation device 500, DB server 502, and application server 503 each include a processor such as a CPU (Central Processing Unit) as a means of calculation, and main memory as a means of storage. Here, the processor executes various software such as an OS (operating system) and applications (application software). The main memory is a storage area that stores various software and data used for its execution. Furthermore, the parts manufacturing plant location estimation device 500, DB server 502, and application server 503 also include storage such as an HDD (Hard Disk Drive) or SSD (Solid State Drive) as auxiliary storage devices, and a communication interface for communicating with the outside world. They may also include input devices such as a mouse or keyboard, and output devices such as a display.

[0029] Although the parts manufacturing plant location estimation device 500, DB server 502, and application server 503 are shown here as separate devices, they do not necessarily have to be separate devices. For example, the parts manufacturing plant location estimation device 500, DB server 502, and application server 503 may be combined into a single device for processing. Alternatively, for example, the DB server 502 and application server 503 may be combined into a single device for processing. Furthermore, each of the parts manufacturing plant location estimation device 500, DB server 502, and application server 503 may be configured as multiple devices.

[0030] <Data Structure> Next, the data structure used in this embodiment will be described. Figure 2 is a table illustrating an example of a supplier list data table that is received as input from the procurement officer. A supplier list is a list of information about suppliers for products manufactured by the company to which the procurement officer belongs. The illustrated supplier list includes the product name of the product manufactured by the company to which the procurement officer belongs. In this case, the product name is Product A. The supplier list also includes information on primary and secondary suppliers for Product A. Here, the primary and secondary supplier information includes the company name, head office address, part name, model number, and remarks. The supplier list may also include optional items such as links to the supplier company's official website and company codes / corporate numbers that uniquely identify the supplier company. The supplier list contains numerical data, text, or links to detailed data for each item. The definition, category, unit of value, and hierarchical structure of each item may be arbitrary as long as they follow the rules established by the procurement officer. The supplier list may be received from the user terminal 370, or a supplier list generated by the existing system 501 may be received. Alternatively, it may be received from a system linked to the risk visualization system 1. In this embodiment, the received supplier list is stored in the company / risk information (data lake) 301.

[0031] Figure 3 is a table showing an example of search results generated by the Corporate Information Retrieval Unit 200, using the supplier's company name as a keyword. The Corporate Information Search Unit 200 searches for potential supplier factories based on the supplier list shown in Figure 2. The Corporate Information Search Unit 200 searches for potential supplier factories by using the company names included in the supplier list as keywords and searching via the network 400. This makes it possible to obtain potential supplier factories using the supplier list. Furthermore, it becomes easier to obtain potential supplier factories by searching using the company names included in the supplier list as keywords. Here, the results of a search by the Corporate Information Search Unit 200 using "B Corp." in Figure 2 as a keyword are shown. These search results can be treated as a list of potential supplier factories. The illustrated table consists of the company name, location, industry information, and URL of the company's homepage for the potential supplier factory. Commercial data such as the Corporate Information Database 300 and Open Data 350 can be used for the search. However, the search destination is not limited to these; information from electronic telephone directories obtained via the network 400 and company location information registered on online maps may also be used. Furthermore, although the search results shown here do not distinguish between uppercase and lowercase letters, the distinction between uppercase and lowercase letters, full-width and half-width characters, etc., can be arbitrarily selected. Also, in the following description, even if the description is omitted in the search process or matching judgment process described in the present invention, similar character distinctions may be selectively performed.

[0032] Figure 4 is a table diagram of a data table that manages information about the company to which a procurement officer belongs. The table shown is a management table for the company to which the procurement officer belongs. The company information includes at least the company name and industry. For the industry information to be registered, all industries related to the company may be selected and registered. Here, the industries are listed separately as the primary industry and non-primary industries. The table shown can be registered directly by the procurement officer, but it can also be obtained by referring to the company information database via Network 400. In this embodiment, the company information shown in Figure 4 is stored in the company / risk information (data lake) 301.

[0033] Figure 5 is a diagram showing an example of a data table of transaction relationships between different industries. The illustrated table records the transaction relationship between one industry and another. The items representing the transaction relationship can be arbitrary, and in this embodiment, the transaction amount for the past year is used, and the transaction amount between industries corresponding to the major classifications of the Japan Standard Industrial Classification is used in Japanese yen (unit: 100 million yen). In other words, the illustrated table uses the industrial classification code of the major classifications of the Japan Standard Industrial Classification, and the transaction amount between the shipper and the recipient is recorded as the transaction relationship between one industry and another. However, the source of the data (e.g., the International Standard Industrial Classification or the North American Industrial Classification System) and the scope of the data used (e.g., within a single year or the most recent three years) can be arbitrarily determined. Note that this embodiment shows an example using the Japan Standard Industrial Classification as data, but other data including items that represent transaction relationships may be used.

[0034] Figure 6 is a diagram showing an example of a data table for inter-industry transaction relationship scores. The inter-industry transaction relationship score is a numerical representation of the relationship between multiple industries. The relationship is considered to be stronger when the transaction amount is large, as shown in Figure 5, and weaker when the transaction amount is small. Therefore, the transaction relationship score calculation unit 202 calculates the inter-industry transaction relationship score based on the transaction amount between industries. That is, when the transaction amount between each industry is large and the transaction relationship is large, the inter-industry transaction relationship score will be high, and when the transaction amount between each industry is small and the transaction relationship is small, the inter-industry transaction relationship score will be low. In this embodiment, the inter-industry transaction relationship score uses a numerical value that takes a maximum value of 10, calculated using the transaction amount between industries in a certain year, as shown in Figure 5. As shown in Figure 6, the inter-industry transaction relationship score will be high when the transaction amount is large between industries, so the scale of goods and services between industries can be quantitatively evaluated. In addition, this also includes the inter-industry transaction relationship score when the industries are the same (for example, from electrical machinery and equipment manufacturing to electrical machinery and equipment manufacturing as exemplified in the figure). However, the inter-industry transaction relationship score is not limited to this; a score calculated using a comparison table of classification items in the Japan Standard Industrial Classification and industry items used in comparable industry pricing calculations, or using transaction relationship data between standard industrial classifications listed in trade statistics (e.g., transaction relationship, transaction volume), may also be used. Alternatively, procurement personnel may input appropriate values ​​for the inter-industry transaction relationship score.

[0035] <Detailed description of the parts manufacturing plant location estimation device 500> Next, we will explain in detail the parts manufacturing plant location estimation device 500. Figure 7 shows the processing flow of the parts manufacturing plant location estimation device 500 in the risk visualization system 1. As shown in Figure 7, the parts manufacturing plant location estimation device 500 first obtains a supplier list as shown in Figure 2 (S701). Next, the parts manufacturing plant location estimation device 500 uses the supplier's company name as a keyword to determine whether at least one of the company information and the registered content of public certifications can be obtained from the company information database 300 or open data 350 (S702). In this embodiment, the following shows the case where the registered content of public certification information is searched. In this embodiment, for example, the registered information of the international standard ISO9001 is referred to. However, it is not limited to this.

[0036] As a result, if it is possible to obtain the information (Yes in S702), the parts manufacturing plant location estimation device 500 obtains a list of locations and factories owned by the supplier's candidate companies, along with the manufactured items and functions of each location and factory (S703). When referring to the registration information of the international standard ISO9001, the information can be obtained in the format of {"Factory A: Manufacturing of square resistors", "Factory B: Manufacturing of lighting fixture components", ...}.

[0037] Next, the parts manufacturing plant location estimation device 500 uses the industry estimation unit 201 to estimate the industry corresponding to the major classification of the Japan Standard Industrial Classification from the manufactured items of each base / factory (S704). In this embodiment, for example, an estimation method using a finely tuned large-scale language model is applied to estimate the industry. However, it is not limited to this, and for example, a machine learning model that uses past estimation results as training data may be applied, or the industry may be estimated by creating a correspondence table in advance. The processing in the industry estimation unit 201 in this embodiment involves providing a list of major classifications of the Japan Standard Industrial Classification as training data and performing additional training. By inputting the manufactured items and functions of each base / factory acquired in S703 into the additionally trained large-scale language model, it outputs which major classification of the Japan Standard Industrial Classification the business content of each base / factory corresponds to. When referring to the registration information of the international standard ISO9001, it is estimated as follows: {"Factory A: Electronic components, devices, and electronic circuits manufacturing industry", "Factory B: Electrical machinery and equipment manufacturing industry", ...}.

[0038] Next, the parts manufacturing plant location estimation device 500 uses the parts supplier industry estimation unit 204 to estimate the industry of the supplier that manufactures the parts, using the parts name and model number included in the supplier list (S705). In S705, the parts name and model number are obtained from catalog data or internet search via the network 400. If the parts name can be obtained from catalog data, the industry of the manufacturer that produces the parts can sometimes be obtained as supplementary information, but if it is obtained from an internet search, the industry cannot be estimated. In this embodiment, an example is shown in which estimation is performed using a large-scale language model that has been further trained using catalog data as training data. The further trained large-scale language model accepts results obtained from catalog data or the internet via the network 400 as input, using the parts name (e.g., steel screw) and model number (e.g., AB-123) as search keywords, and outputs the industry of the supplier that manufactures the parts (e.g., metal manufacturing). Furthermore, the technology used for estimation is not limited to the large-scale language model described above. For example, a correspondence table between part names or model numbers and supplier industries may be used, or estimation may be performed using machine learning models. This makes it possible to compare the industry of each supplier's factory estimated from the manufactured items with the industry of the supplier estimated from the part names or model numbers, using the same evaluation axis of the Japan Standard Industrial Classification (JISA).

[0039] Next, the parts manufacturing plant location estimation device 500 uses the parts manufacturing plant estimation unit 206 to score the industry of the supplier's factory estimated from the manufactured items and the industry of the supplier's factory estimated from the part name and model number using the inter-industry transaction relationship score shown in Figure 6, thereby obtaining the factory with the highest score (S706). Then, it estimates the location of the factory with the highest score as the location of the factory that manufactures the part. However, the method of comparing the factory list and the data of each factory's function obtained in S702 with the suppliers that manufacture the parts obtained in S703 is not limited to the method in S706. Alternatively, the words for the part name and the manufactured items and functions of each factory may be vectorized and replaced with word embeddings such as gestalt pattern matching, distance indicators using final editing cost, or cosine similarity between word vectors for determination. Alternatively, a method may be used in which a device that accepts the part name and the list of functions of each factory as input using a large-scale language model is used to generate the factories that manufacture the parts. In this case, a method may be used to improve the accuracy of generating the factories that manufacture the parts by having a large-scale language model pre-train it with a systematized data table of parts that are commonly recognized by supplier companies according to international treaties such as the Unified System for the Name and Classification of Goods, for example, the Harmonized System (HS) code in this embodiment.

[0040] Then, the estimated locations of the parts manufacturing plants are reflected in the supplier list (S707). The process in S703-S707 involves obtaining a list of factory locations and functions registered in the official certification if the supplier's parts manufacturing plant has obtained official certification, and then estimating the location of the parts manufacturing plant by estimating which plant actually manufactures the parts based on the items manufactured by each plant.

[0041] On the other hand, if at least one of the relevant company information and the registered contents of the public certification cannot be obtained in S702 (No in S702), the parts manufacturing plant location estimation device 500 searches for the supplier's company information via the network 400 using the company information search unit 200 and obtains candidate factories for the supplier (S708). If No in S702, for example, information on companies other than "B Corp." in Figure 2 could be obtained from the company information database 300 or open data 350, but it is difficult to obtain information on "B Corp." because it is a small factory. In this case, the parts manufacturing plant location estimation device 500 estimates the location of the manufacturing plant for the parts manufactured by the supplier using an estimation method that utilizes the company information search unit 200, industry estimation unit 201, transaction relationship score calculation unit 202, parts / model number estimation unit 203, parts supplier industry estimation unit 204, industry similarity calculation unit 205, and parts manufacturing plant estimation unit 206.

[0042] The search results for "B Corp." as a keyword in the Corporate Information Search Unit 200 are shown in Figure 3. When searching using Network 400, for example, company names including factory names, address information, industry information, and URLs of information sources can be obtained from registered information in electronic telephone directories and online maps, as well as corporate registration information. The company information retrieval unit 200 then determines whether or not there is only one potential supplier factory found (S709). If there is only one location (Yes in S709), the location of this factory candidate is used as the estimated location of the supplier's parts manufacturing plant, and the process is terminated. On the other hand, if multiple supplier factory candidates are found (No in S709), the following process is performed. In this case, as shown in Figure 3, multiple supplier factory candidates are searched for. The parts manufacturing factory location estimation device 500 then first uses the industry estimation unit 201 and the transaction relationship score calculation unit 202 to narrow down the supplier factory candidates shown in Figure 3.

[0043] Figure 8 is a flowchart showing the process of narrowing down the list of potential supplier factories. The industry estimation unit 201 performs a process to align the notation of the industry information column in the data table in Figure 3 with the intermediate classifications of the Japan Standard Industrial Classification. In this embodiment, the cosine similarity of word embeddings between the document described in the industry information and the document described in the intermediate classification of the Japan Standard Industrial Classification is compared, and the intermediate classification of the Japan Standard Industrial Classification with the highest similarity (for example, food manufacturing) is used as the industry information. Also, as shown in Figure 4, since the information of the company to which the procurement officer belongs is pre-registered, it is similarly aligned with the intermediate classification of the Japan Standard Industrial Classification. The industry of ABC Corporation in Figure 4, "Electrical machinery manufacturing, information processing equipment, motor equipment, scientific instruments, metalworking machinery," is estimated to be "Electrical machinery and equipment manufacturing, information and communication machinery and equipment manufacturing, chemical industry, metal product manufacturing," which is an intermediate classification of the Japan Standard Industrial Classification (S801). In this case, industries can be compared on the same evaluation axis.

[0044] The transaction relationship score calculation unit 202 compares the industry of the company to which the procurement officer in Figure 4 belongs with the industry of the search result using "B Corp." as a keyword in Figure 3, and calculates the inter-industry transaction relationship score. For example, the electrical machinery and equipment manufacturing industry has a large annual transaction amount with the electronic component manufacturing industry, which is a component of the electrical machinery and equipment, so it is likely that they are doing business with that industry. On the other hand, agriculture has a small annual transaction amount with the electrical machinery and equipment manufacturing industry, so it has a low inter-industry transaction relationship score and is unlikely to be doing business with that industry. In this embodiment, we have shown an example of comparing companies by aligning their industry categories with the major classifications of the Japan Standard Industrial Classification. However, it is also possible to compare industries and calculate scores by considering the parent-child relationships in the classification system using minor classification items.

[0045] Figure 9 shows the output results of the transaction relationship score calculation unit 202. As shown in Figure 3, the industry of "B Corp. Sumida Factory" is determined to be "Electrical Machinery and Equipment Manufacturing" by the Industry Estimation Unit 201. Referring to the data table of calculated inter-industry transaction relationship scores shown in Figure 6, the inter-industry transaction relationship score between "Electrical Machinery and Equipment Manufacturing," the industry of the company to which the procurement officer belongs, and "Electrical Machinery and Equipment Manufacturing," the industry of "B Corp. Sumida Factory," is calculated to be 7.7 (S801). Since there are four industries to which the company to which the procurement officer belongs, the inter-industry transaction relationship score is calculated for all combinations, and the result with the highest inter-industry transaction relationship score is determined as the calculation result (S802, S803).

[0046] In this embodiment, we show an example where only the results from the data table shown in Figure 3 where the inter-industry relationship score is above a threshold (0.5) are used. In the example in Figure 9, #1 "B Corp. Sumida Factory", #2 "B Corp. Chiba Factory", and #3 "B Corp. Daiichi Factory" are used because their thresholds are above 0.5, but #4 "B Corp. Naha Sales Office" is not used because its threshold is below 0.5. This narrows down the list of potential supplier factories shown in Figure 3. In this case, the list of potential supplier factories can be narrowed down by focusing on the similarity of the industries of companies that have trading relationships in the supply chain. In other words, if the industries are similar, the probability of trading is high, and the inter-industry relationship score will be high, but if they are not similar, the inter-industry relationship score will be low, and the probability of trading is low. The list of potential supplier factories is then narrowed down based on the inter-industry relationship score. From this perspective, the inter-industry transaction relationship score shown in Figure 9 can be considered to represent the similarity between the company to which the procurement officer in Figure 4 belongs (in this case, "ABC Corporation") and the company in Figure 3 (in this case, "B Corp."). The threshold can be read from a user definition, or it can be automatically changed in response to user feedback. The threshold can also be made variable according to user specifications. Furthermore, the selection criteria for the results can be arbitrary; for example, only the top results may be used, or the user may specify them arbitrarily.

[0047] Note that the process in S801 in Figure 8 corresponds to the process in S710 in Figure 7, in which the industry estimation unit 201 estimates the industry of the candidate supplier factory. Also, the processes in S802 and S803 in Figure 8 correspond to the process in S711 in Figure 7, in which the transaction relationship score calculation unit 202 narrows down the candidate supplier factory based on the inter-industry transaction relationship score between the industry of the company to which the user belongs and the industry of the company that is the candidate supplier factory.

[0048] Returning to Figure 7, the part / model number estimation unit 203 receives a string of part names or model numbers listed in the supplier list as input and obtains part information via the network 400 (S712). As mentioned above, part information includes, for example, the material, price, and delivery date of the part. In this embodiment, for example, online part catalogs and part information databases are referred to as the search targets. However, the search targets may also be internet search results obtained via the network 400, or databases within the organization to which the procurement officer belongs. Furthermore, the search results for part names or model numbers may be stored in the company / risk information (data lake) 301 and used for subsequent searches.

[0049] Next, the parts supplier industry estimation unit 204 estimates the industry of the candidate supplier factory based on the parts identification information (S713). Figure 10 shows a schematic diagram of the processing flow of the parts supplier industry estimation unit 204. The parts supplier industry estimation unit 204 is a processing unit that estimates which of the search results generated by the company information search unit 200 shown in Figure 3, using the company names of potential supplier factories as keywords, is most likely to be a supplier company. The parts supplier industry estimation unit 204 estimates the industry of a potential supplier factory based on at least one of the part name and model number (hereinafter sometimes simply referred to as "part name / model number") as part identification information. In this embodiment, the parts supplier industry estimation unit 204 uses data from three different systems with different purposes to estimate the industry of the supplier that manufactures the parts from the part name / model number information. Here, the parts supplier industry estimation unit 204 performs estimation in three ways: (a) direct estimation of the industry based on the part name / model number (S1001), (b) two-step estimation of the industry through mapping the part name / model number to one different data system (S1002), and (c) three-step estimation of the industry through mapping the part name / model number to two different data systems (S1003). This allows estimation to be performed by combining multiple data based on the part name / model number, and enables industry estimation from multiple perspectives.

[0050] Figure 11 shows the details of the processing flow of the parts supplier industry estimation unit 204. In this embodiment, the part / model number estimation unit 203 determines whether or not part information can be obtained from the Internet or a parts catalog via the network 400 using the part name / model number as a keyword (S1101). Then, if part information can be obtained from a parts catalog or the internet (Yes in S1101), the parts supplier industry estimation unit 204 determines whether or not the supplier's industry information is included as part information, in addition to information such as the material, price, and delivery date of the part (S1102). As a result, if supplier industry information is provided (Yes in S1102), the parts supplier industry estimation unit 204 uses the acquired industry information as the supplier's industry name (S1103). In this embodiment, if supplier industry information is provided (Yes in S1102), processing S1104 is also performed along with S1103.

[0051] Conversely, if supplier industry information is not provided (No in S1102), the parts supplier industry estimation unit 204 obtains the corresponding HS code using the part name as a keyword (S1104). In this embodiment, this function is implemented using a large-scale language model that accepts a part name as input and generates the corresponding HS code. However, this method is not limited to this, and for example, a correspondence table between part names and HS codes may be used, or it may be linked with an external service that allows searching for HS codes from part names. Then, the HS code subcategory name is used as the supplier's industry name (S1105).

[0052] On the other hand, in S1101, there are cases where part information cannot be obtained from a parts catalog or the internet (No in S1102). This applies, for example, when a part has a unique model number or is a custom-made item. In this case, the parts supplier industry estimation unit 204 checks whether the part name / model number includes a general name (for example, a standard name such as "M5" or "hex bolt") or a material (for example, "SUS304" or "brass") (S1106). If included (Yes in S1106), the parts supplier industry estimation unit 204 obtains the corresponding HS code using the generic name / material as a keyword (S1107). In this embodiment, this function is implemented using a large-scale language model that accepts the generic name / material as input and generates the corresponding HS code. Then, the major classification name of the HS code is used as the industry name of the supplier (S1108).

[0053] Furthermore, if the part name / model number in S1106 does not include a general name / material (No in S1106), it is impossible to estimate the industry, so the part supplier industry estimation unit 204 notifies the user terminal 370 via the network 400 that the industry cannot be estimated (S1109).

[0054] In the industry estimation flow shown in Figure 11, the parts supplier industry estimation unit 204 either directly estimates the industry of a candidate supplier's factory from the part name / model number, or estimates it through mapping to data in a different system. In this case, estimation can be performed by combining multiple data based on the part name / model number. If parts information can be obtained, the parts supplier industry estimation unit 204 directly estimates the industry of a candidate supplier's factory from the part name / model number; if parts information cannot be obtained, it estimates it through mapping to data in a different system. In this case, even if the industry of a candidate supplier's factory cannot be directly estimated based on the part name / model number, estimation becomes possible through other methods.

[0055] Furthermore, the processing flow of the parts supplier industry estimation unit 204 in Figure 11 can result in either two estimation results (S1103 and S1105), one estimation result (S1105 or S1108), or no industry estimation (S1109). In other words, the number of industry estimation results is one of 0, 1, or 2.

[0056] Figure 12 is a diagram showing a data table that illustrates the estimation results when (a) the industry is directly estimated based on the part name / model number. The illustrated data table includes items for part name, model number, and estimated industry. Here, using the model number "X01L" as a keyword, we find a match in the company information database 300 and show the results of directly estimating the industry. Specifically, we show that for the part with the part name and model number "X01L", the estimated industry is "screw manufacturing". In this embodiment, the part name / model number is used as a keyword, but it is not limited to this; any information that can uniquely identify the traded item is acceptable. For example, if part information can be retrieved from a parts information database or online catalog, the industry included in the property information is used to estimate the industry, which is then assigned as the result.

[0057] Figure 13 is a diagram showing a data table illustrating the estimation results when the industry is estimated in two steps through (b) mapping part name / part number to data in one different system. The illustrated data table includes the following items: part name / model number, estimated product name, industry classification code, and estimated industry. In this embodiment, the part name / model number is used as a keyword, but it is not limited to this; any information that can uniquely identify the traded item is acceptable. If industry information is not listed in the part information database or online catalog, the part supplier industry estimation unit 204 converts the data into a different system using the category and tag information to which the part belongs (e.g., screws and bolts > steel screws > flat screws > X01L) and estimates the industry of the supplier that manufactures the part. In this embodiment, an example is shown in which the category to which the part belongs is obtained from the part name / model number, and the industry is estimated via the HS code, which is a different system of data. By using the HS code, it becomes easier to estimate the industry of a candidate supplier factory. "X01L" is estimated to be the product name "flat screw," but it is difficult to estimate the sub-classification of the Japan Standard Industrial Classification from the keyword "flat screw." Therefore, by converting "steel screws" to the corresponding HS code "H73.18," it is possible to estimate the "iron and steel industry," which is the subcategory of the Japan Standard Industrial Classification corresponding to HS code "H73.18." In other words, in this case, the supplier industry name is estimated through a two-step process: part name / model number → HS code → industry. That is, the industry is estimated from the part name through two mapping steps. In this embodiment, information in which the item was estimated as data from a different system was used, but this is not the only way to do so. For example, international standards or industry standards may be referred to.

[0058] Figure 14 is a diagram showing a data table illustrating the estimation results when the industry is estimated in three stages through mapping from part name / part number to data from two different systems. The illustrated data table includes items for part name / model number, component parts, industry classification code, and estimated industry. In this embodiment, part name / model number is used as a keyword, but it is not limited to this; any information that can uniquely identify the traded item is acceptable. The part name and model number columns in the supplier list may contain information that cannot be obtained from the part information database or online catalog. For example, if a part does not have a model number, such as a unique model number linked only within the supplier company or a custom-made product, the part name and model number columns in the supplier list will contain the material or general name of the part, such as "plastic cable" or "SUS304 bolt." Figure 14 shows an example where "no model number" is indicated, and information on similar parts is obtained from the material or general name of the part, the category to which the similar parts belong is obtained, and the industry is estimated via the HS code, which is a different data system. In this embodiment, the parts supplier industry estimation unit 204 uses a large-scale language model to perform an HS code search using the general name / material as a keyword (S1106, S1107 in Figure 11). The parts supplier industry estimation unit 204 then assigns the major HS code category name as the supplier industry name (S1108 in Figure 11). In other words, in this case, the supplier industry name is estimated through a three-step configuration: parts name / model number → constituent materials → HS code → industry. That is, the industry is estimated from the parts name through three mapping steps. However, this estimation method is not limited to this method. For example, the supplier industry name may be estimated through a three-step configuration: parts name / model number → general name → HS code → industry.

[0059] Furthermore, if the supplier list only contains unique part numbers and there are no searchable keywords such as material names, the procurement officer will be informed that the industry cannot be estimated (S1109). However, the data used to estimate the industry from the part name / part number is not limited to that referenced in this embodiment; for example, trade statistics data such as the Standard International Trade Commodity Classification (SITC code) or BEC code, or industry-specific classification systems may be used. Input from the procurement officer may also be accepted.

[0060] Returning to Figure 7, the industry similarity calculation unit 205 calculates an inter-industry transaction relationship score between the industry of the supplier's factory candidate and the industry of the supplier's factory candidate estimated by the parts supplier industry estimation unit 204 (S714). In other words, the industry similarity calculation unit 205 calculates an inter-industry transaction relationship score between the industry estimated using the industry estimation unit 201 from the industry information in Figure 3 and the industry estimated by the processing flow of the parts supplier industry estimation unit 204 in Figure 11.

[0061] Figure 15 shows a data table where inter-industry transaction relationship scores are assigned to the search results from Figure 3. Figure 15 is a table showing the search results using the supplier names shown in Figure 3 as keywords, with the addition of inter-industry transaction relationship scores. However, as explained in Figure 9, the process of narrowing down the candidate factories of the suppliers shown in Figure 3 is performed using the industry estimation unit 201 and the transaction relationship score calculation unit 202, so "B Corp. Naha Sales Office" (#4) is not included. Figure 15 shows the cases where (x) the result of direct estimation of the industry by part name / model number (the estimation result in (a) above) and (y) the result of estimating the industry through data from a different system from the part name / model number (the estimation result in (b) above) were obtained. The result of direct estimation of the industry by part name / model number (x) is calculated using the inter-industry transaction relationship score using the industry assigned by S1103 in Figure 11. Similarly, the result of estimating the industry through data from a different system from the part name / model number (y) is calculated using the inter-industry transaction relationship score using the industry assigned by S1105 in Figure 11.

[0062] Returning to Figure 7, the parts manufacturing plant estimation unit 206 selects supplier plant candidates based on the inter-industry transaction relationship score calculated by the industry similarity calculation unit 205, and estimates the location of the selected supplier candidate as the location of the parts manufacturing plant that the supplier produces (S715).

[0063] Figure 16 shows the processing flow of the parts manufacturing plant estimation unit 206. As explained in Figure 11, the number of estimated industry types is one of 0, 1, or 2. The parts manufacturing plant estimation unit 206 determines the number of estimated industry types (S1601) and performs the processes in S1602, S1603, and S1604, respectively. If no inter-industry transaction relationship scores can be estimated (i.e., the number of estimated industry results is 0), the parts manufacturing plant estimation unit 206 assigns a "parts plant estimation impossible" label (S1602). If one inter-industry transaction relationship score can be estimated (i.e., the number of estimated industry results is 1), the parts manufacturing plant estimation unit 206 generates the address of the supplier candidate to which the inter-industry transaction relationship score has been assigned as the estimated result of the supplier company's factory location candidate (S1603). If two inter-industry relationship scores can be estimated (i.e., the number of estimated industry results is two), the parts manufacturing plant estimation unit 206 generates a candidate supplier factory that has the highest inter-industry relationship score when estimated using method (b) as the estimated result for the factory location of the parts manufactured by the supplier (S1604). In other words, the parts manufacturing plant estimation unit 206 selects the supplier factory candidate with the highest inter-industry relationship score and estimates the location of the selected supplier factory candidate as the location of the factory that manufactures the parts manufactured by the supplier. This allows the user to be presented with the most likely location for the supplier factory candidate.

[0064] The parts manufacturing plant estimation unit 206 then saves the supplier company's factory location as a candidate if the inter-industry transaction relationship score is higher than a threshold (for example, 0.7) (S1605). This can also be said that the parts manufacturing plant estimation unit 206 further selects supplier factory candidates that are above a predetermined threshold (in this case, 0.7). This allows the user to select a corrected candidate even if the estimation result is incorrect. However, the priority order and combination of inter-industry transaction relationship scores used to estimate parts manufacturing plants are not limited to the definition in this embodiment, and may be defined, for example, using a weighted average or predefined weighting coefficients.

[0065] Figure 17 shows a data table that reflects the location of the parts manufacturing plant estimated in S707 of Figure 7 in the supplier list. This embodiment shows a case where the estimated location of the parts manufacturing plant is added to the supplier list shown in Figure 2. As shown in Figure 17, in this embodiment, the original data is given columns for estimated part name, plant name, plant location, data source, and other candidate columns. However, the columns to be added are not limited to the form shown. The "other candidate" column shows a list of plant candidates for suppliers whose inter-industry relationship score is above a threshold. This allows procurement personnel to select corrective candidates from the list even if the estimation result is incorrect. In this embodiment, an example is shown where the threshold is set to 0.7, making it possible to obtain approximately the top 5 suppliers based on their inter-industry relationship score. This threshold may be defined in advance, or it may be dynamically generated so that approximately the top 5 suppliers based on their inter-industry relationship score are selected.

[0066] In the processing flow shown in Figure 7, if a supplier included in the supplier list has not obtained official certification (No in S702), the company information retrieval unit 200 searches for potential supplier factories (S708). If the supplier has obtained official certification, the company information retrieval unit estimates the industry of the supplier's factory from the manufactured items registered in the official certification (S704). This allows the company information retrieval unit to estimate the industry of the supplier's factory based on the official certification if the supplier has obtained it, and to estimate the industry of the supplier's factory by searching for potential supplier factories even if the supplier has not obtained official certification.

[0067] According to the configuration described above, a parts manufacturing plant location estimation device 500 can be provided that can estimate the location of the manufacturing plant for parts produced by a supplier. In this case, the location of the manufacturing plant for parts missing from the supplier list can be automatically assigned. Furthermore, by reducing the amount of work required for procurement personnel to gather information, it becomes possible to make rapid risk assessments of the supply chain. Moreover, by combining data with different uses and estimating the location of the manufacturing plant in multiple stages, estimation from multiple perspectives can be performed.

[0068] In the above-described configuration, the functional units of the parts manufacturing plant location estimation device 500 were referred to as the company information search unit 200, industry estimation unit 201, transaction relationship score calculation unit 202, parts / model number estimation unit 203, parts supplier industry estimation unit 204, industry similarity calculation unit 205, and parts manufacturing plant estimation unit 206. However, these are names used for convenience and the functions are not limited to those referred to by these names. Other names may also be used. For example, the plant candidate search unit 200, first industry estimation unit 201, first score calculation unit 202, parts information search unit 203, second industry estimation unit 204, second score calculation unit 205, and location estimation unit 206 may also be used.

[0069] <Explanation of information processing method> The processing performed by the parts manufacturing plant location estimation device 500 is realized through the cooperation of software and hardware resources. Specifically, a processor such as a CPU installed in the parts manufacturing plant location estimation device 500 loads programs that realize each function of the parts manufacturing plant location estimation device 500 into main memory and executes them to realize each of these functions. Therefore, the processing performed by the parts manufacturing plant location estimation device 500 described above can be understood as an information processing method in which the processor executes a program stored in memory to calculate an inter-industry transaction relationship score representing the relationship between transaction relationships between multiple industries, estimates the industry of a supplier's factory candidate from the parts, calculates an inter-industry transaction relationship score between the estimated supplier's factory candidate's industry and the calculated inter-industry transaction relationship score, selects a supplier's factory candidate based on the calculated inter-industry transaction relationship score, and estimates the location of the selected supplier candidate as the location of the manufacturing plant for the parts manufactured by the supplier. This makes it possible to provide an information processing method that can estimate the location of the manufacturing plant for the parts manufactured by a supplier.

[0070] Furthermore, the program running on the parts manufacturing plant location estimation device 500 can be understood as a program that enables the computer to perform the following functions: calculate an inter-industry relationship score representing the relationship between trading relationships between multiple industries; estimate the industry of a supplier's factory candidate from the parts; calculate an inter-industry relationship score between the supplier's factory candidate industry and the estimated supplier's factory candidate industry; and select a supplier's factory candidate based on the calculated inter-industry relationship score, and estimate the location of the selected supplier candidate as the location of the manufacturing plant for the parts manufactured by the supplier. This enables the computer to realize the function of estimating the location of the manufacturing plant for the parts manufactured by the supplier.

[0071] Furthermore, the program that implements this embodiment can be provided not only by means of communication, but also by being stored on a recording medium such as a CD-ROM. [Explanation of Symbols]

[0072] 1…Risk Visualization System, 200…Company Information Retrieval Unit, 201…Industry Estimation Unit, 202…Transaction Relationship Score Calculation Unit, 203…Parts / Model Number Estimation Unit, 204…Parts Supplier Industry Estimation Unit, 205…Industry Similarity Calculation Unit, 206…Parts Manufacturing Plant Estimation Unit, 303…Inter-Industry Similarity, 500…Parts Manufacturing Plant Location Estimation Device, 501…Existing System

Claims

1. A transaction relationship score calculation unit calculates an inter-industry transaction relationship score that represents the relationship between transaction relationships between multiple industries, Regarding potential supplier factories, the parts supplier industry estimation unit estimates the industry of the potential supplier factory based on parts identification information, An industry similarity calculation unit calculates an inter-industry transaction relationship score between the industry of a candidate supplier factory and the industry of a candidate supplier factory estimated by the parts supplier industry estimation unit, Based on the inter-industry transaction relationship score calculated by the aforementioned industry similarity calculation unit, a parts manufacturing plant estimation unit selects candidate supplier factories and estimates the location of the selected candidate supplier as the location of the manufacturing plant for the parts manufactured by the supplier. An information processing device equipped with the following features.

2. The information processing apparatus according to claim 1, wherein the transaction relationship score calculation unit narrows down the supplier factory candidates based on the inter-industry transaction relationship score between the industry of the company to which the user belongs and the industry of the supplier factory candidate, and subjects the narrowed-down supplier factory candidates to processing by the parts supplier industry estimation unit.

3. The information processing apparatus according to claim 2, further comprising an industry estimation unit for estimating the industry of a supplier's potential factory.

4. The information processing device according to claim 1, wherein the parts supplier industry estimation unit directly estimates the industry of a candidate supplier factory from at least one of the parts name and the part number, or estimates it through mapping to data of a different system.

5. It further includes a part and model number estimation unit that acquires part information, The information processing device according to claim 4, wherein the parts supplier industry estimation unit, if it can obtain the parts information, directly estimates the industry of a candidate supplier factory from at least one of the parts name and part number, and if it cannot obtain the parts information, it estimates it through mapping to data of a different system.

6. The information processing device according to claim 4, wherein the data of the different systems includes the export / import statistical item number.

7. The information processing device according to claim 1, further comprising a company information retrieval unit that searches for potential supplier factories based on a supplier list, which is a list of information about suppliers of products manufactured by the company to which the user belongs.

8. The information processing apparatus according to claim 7, wherein the company information retrieval unit searches for potential supplier factories by searching for the company names of suppliers included in the supplier list as keywords.

9. The information processing apparatus according to claim 7, wherein if a supplier included in the supplier list has not obtained official certification, the company information retrieval unit searches for potential supplier factories, and if the supplier has obtained official certification, the business type of the supplier factory is estimated from the manufactured items registered in the official certification.

10. The information processing apparatus according to claim 1, wherein the parts manufacturing plant estimation unit selects a supplier factory candidate that has the highest inter-industry transaction relationship score, and estimates the location of the selected supplier factory candidate as the location of a parts manufacturing plant manufactured by the supplier.

11. The information processing apparatus according to claim 10, wherein the parts manufacturing plant estimation unit further selects supplier plant candidates that are above a predetermined threshold.

12. The information processing apparatus according to claim 1, wherein the transaction relationship score calculation unit calculates an inter-industry transaction relationship score based on the transaction amount between industries.

13. The processor executes the program stored in memory, We calculate an inter-industry relationship score that represents the relationship between business relationships between multiple industries. Regarding potential supplier factories, we estimate the industry of the potential supplier factory based on the parts used. We calculate an inter-industry transaction relationship score between the industry of the supplier's potential factory and the estimated industry of the supplier's potential factory. Based on the calculated inter-industry transaction relationship score, potential supplier factories are selected, and the location of the selected supplier factory is estimated to be the location of the factory that manufactures the parts produced by that supplier. Information processing methods.

Images